unicode-org · aphillips · Jan 13, 2024 · Jan 12, 2024 · Jan 13, 2024 · Jan 13, 2024
diff --git a/spec/data-model/README.md b/spec/data-model/README.md
@@ -135,24 +135,33 @@ interface LiteralExpression {
   type: "expression";
   arg: Literal;
   annotation?: FunctionAnnotation | UnsupportedAnnotation;
+  attributes?: Attribute[];
 }
 
 interface VariableExpression {
   type: "expression";
   arg: VariableRef;
   annotation?: FunctionAnnotation | UnsupportedAnnotation;
+  attributes?: Attribute[];
 }
 
 interface FunctionExpression {
   type: "expression";
   arg?: never;
   annotation: FunctionAnnotation;
+  attributes?: Attribute[];
 }
 
 interface UnsupportedExpression {
   type: "expression";
   arg?: never;
   annotation: UnsupportedAnnotation;
+  attributes?: Attribute[];
+}
+
+interface Attribute {
+  name: string;
+  value?: Literal | VariableRef;
 }
 ```
 
@@ -219,7 +228,7 @@ that the implementation attaches to that _annotation_.
 ```ts
 interface UnsupportedAnnotation {
   type: "unsupported-annotation";
-  sigil: "!" | "@" | "%" | "^" | "&" | "*" | "+" | "<" | ">" | "?" | "~";
+  sigil: "!" | "%" | "^" | "&" | "*" | "+" | "<" | ">" | "?" | "~";
   source: string;
 }
 ```
@@ -241,19 +250,22 @@ interface MarkupOpen {
   kind: "open";
   name: string;
   options?: Option[];
+  attributes?: Attribute[];
 }
 
 interface MarkupStandalone {
   type: "markup";
   kind: "standalone";
   name: string;
   options?: Option[];
+  attributes?: Attribute[];
 }
 
 interface MarkupClose {
   type: "markup";
   kind: "close";
   name: string;
+  attributes?: Attribute[];
 }
 ```
 

diff --git a/spec/data-model/message.dtd b/spec/data-model/message.dtd
@@ -24,8 +24,8 @@
 <!ELEMENT pattern (#PCDATA | expression | markup)*>
 
 <!ELEMENT expression (
-  ((literal | variable), (functionAnnotation | unsupportedAnnotation)?) |
-  functionAnnotation | unsupportedAnnotation
+  ((literal | variable), (functionAnnotation | unsupportedAnnotation)?, attribute*) |
+  ((functionAnnotation | unsupportedAnnotation), attribute*)
 )>
 
 <!ELEMENT literal (#PCDATA)>
@@ -43,8 +43,11 @@
 <!ELEMENT unsupportedAnnotation (#PCDATA)>
 <!ATTLIST unsupportedAnnotation sigil CDATA #REQUIRED>
 
+<!ELEMENT attribute (literal | variable)?>
+<!ATTLIST attribute name NMTOKEN #REQUIRED>
+
 <!-- A <markup kind="close"> MUST NOT contain any <option> elements -->
-<!ELEMENT markup (option)*>
+<!ELEMENT markup (option*, attribute*)>
 <!ATTLIST markup
   kind (open | standalone | close) #REQUIRED
   name NMTOKEN #REQUIRED

diff --git a/spec/data-model/message.json b/spec/data-model/message.json
@@ -35,6 +35,22 @@
       },
       "required": ["name", "value"]
     },
+    "attributes": {
+      "type": "array",
+      "items": {
+        "type": "object",
+        "properties": {
+          "name": { "type": "string" },
+          "value": {
+            "oneOf": [
+              { "$ref": "#/$defs/literal" },
+              { "$ref": "#/$defs/variable" }
+            ]
+          }
+        },
+        "required": ["name"]
+      }
+    },
 
     "function-annotation": {
       "type": "object",
@@ -50,7 +66,7 @@
       "properties": {
         "type": { "const": "unsupported-annotation" },
         "sigil": {
-          "enum": ["!", "@", "#", "%", "^", "&", "*", "<", ">", "/", "?", "~"]
+          "enum": ["!", "#", "%", "^", "&", "*", "<", ">", "/", "?", "~"]
         },
         "source": { "type": "string" }
       },
@@ -68,7 +84,8 @@
       "properties": {
         "type": { "const": "expression" },
         "arg": { "$ref": "#/$defs/literal" },
-        "annotation": { "$ref": "#/$defs/annotation" }
+        "annotation": { "$ref": "#/$defs/annotation" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "arg"]
     },
@@ -77,23 +94,26 @@
       "properties": {
         "type": { "const": "expression" },
         "arg": { "$ref": "#/$defs/variable" },
-        "annotation": { "$ref": "#/$defs/annotation" }
+        "annotation": { "$ref": "#/$defs/annotation" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "arg"]
     },
     "function-expression": {
       "type": "object",
       "properties": {
         "type": { "const": "expression" },
-        "annotation": { "$ref": "#/$defs/function-annotation" }
+        "annotation": { "$ref": "#/$defs/function-annotation" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "annotation"]
     },
     "unsupported-expression": {
       "type": "object",
       "properties": {
         "type": { "const": "expression" },
-        "annotation": { "$ref": "#/$defs/unsupported-annotation" }
+        "annotation": { "$ref": "#/$defs/unsupported-annotation" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "annotation"]
     },
@@ -112,7 +132,8 @@
         "type": { "const": "markup" },
         "kind": { "const": "open" },
         "name": { "type": "string" },
-        "options": { "$ref": "#/$defs/options" }
+        "options": { "$ref": "#/$defs/options" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "kind", "name"]
     },
@@ -122,7 +143,8 @@
         "type": { "const": "markup" },
         "kind": { "const": "standalone" },
         "name": { "type": "string" },
-        "options": { "$ref": "#/$defs/options" }
+        "options": { "$ref": "#/$defs/options" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "kind", "name"]
     },
@@ -131,7 +153,8 @@
       "properties": {
         "type": { "const": "markup" },
         "kind": { "const": "close" },
-        "name": { "type": "string" }
+        "name": { "type": "string" },
+        "attributes": { "$ref": "#/$defs/attributes" }
       },
       "required": ["type", "kind", "name"]
     },

diff --git a/spec/formatting.md b/spec/formatting.md
@@ -652,6 +652,10 @@ MUST be an empty string.
 Implementations MAY offer functionality for customizing this,
 such as by emitting XML-ish tags for each _markup_.
 
+_Attributes_ are reserved for future standardization.
+Other than checking for valid syntax, they SHOULD NOT 
+affect the processing or output of a _message_.
+
 ### Examples
 
 _This section is non-normative._

diff --git a/spec/message.abnf b/spec/message.abnf
@@ -19,23 +19,26 @@ selector = expression
 variant = key *(s key) [s] quoted-pattern
 key = literal / "*"
 
-expression = literal-expression / variable-expression / annotation-expression
-literal-expression = "{" [s] literal [s annotation] [s] "}"
-variable-expression = "{" [s] variable [s annotation] [s] "}"
-annotation-expression = "{" [s] annotation [s] "}"
+expression = literal-expression
+           / variable-expression
+           / annotation-expression
+literal-expression = "{" [s] literal [s annotation] *(s attribute) [s] "}"
+variable-expression = "{" [s] variable [s annotation] *(s attribute) [s] "}"
+annotation-expression = "{" [s] annotation *(s attribute) [s] "}"
 annotation = function
            / private-use-annotation
            / reserved-annotation
 
-markup       = "{" [s] markup-open [s] ["/"] "}"
-             / "{" [s] markup-close [s] "}"
+markup       = "{" [s] markup-open *(s attribute) [s] ["/"] "}"
+             / "{" [s] markup-close *(s attribute) [s] "}"
 markup-open  = "#" identifier *(s option)
 markup-close = "/" identifier
 
 literal = quoted / unquoted
 variable = "$" name
 function = ":" identifier *(s option)
 option = identifier [s] "=" [s] (literal / variable)
+attribute = "@" identifier [[s] "=" [s] (literal / variable)]
 
 input = %s".input"
 local = %s".local"
@@ -70,14 +73,14 @@ reserved-keyword = "." name
 
 ; Reserve additional sigils for use by future versions of this specification.
 reserved-annotation = reserved-annotation-start reserved-body
-reserved-annotation-start = "!" / "@" / "%" / "*" / "+"
-                          / "<" / ">" / "?" / "~"
+reserved-annotation-start = "!" / "%" / "*" / "+" / "<" / ">" / "?" / "~"
 
 reserved-body  = *([s] 1*(reserved-char / reserved-escape / quoted))
 reserved-char  = %x00-08        ; omit HTAB and LF
                / %x0B-0C        ; omit CR
                / %x0E-19        ; omit SP
-               / %x21-5B        ; omit \
+               / %x21-3F        ; omit @
+               / %x41-5B        ; omit \
                / %x5D-7A        ; omit { | }
                / %x7E-2FFF      ; omit IDEOGRAPHIC SPACE
                / %x3001-D7FF    ; omit surrogates

diff --git a/spec/syntax.md b/spec/syntax.md
@@ -427,6 +427,7 @@ An _expression_ MUST begin with U+007B LEFT CURLY BRACKET `{`
 and end with U+007D RIGHT CURLY BRACKET `}`.
 An _expression_ MUST NOT be empty.
 An _expression_ cannot contain another _expression_.
+An _expression_ MAY contain one more _attributes_.
 
 A **_<dfn>literal-expression</dfn>_** contains a _literal_,
 optionally followed by an _annotation_.
@@ -438,9 +439,9 @@ An **_<dfn>annotation-expression</dfn>_** contains an _annotation_ without an _o
 
 ```abnf
 expression = literal-expression / variable-expression / annotation-expression
-literal-expression = "{" [s] literal [s annotation] [s] "}"
-variable-expression = "{" [s] variable [s annotation] [s] "}"
-annotation-expression = "{" [s] annotation [s] "}"
+literal-expression = "{" [s] literal [s annotation] *(s attribute) [s] "}"
+variable-expression = "{" [s] variable [s annotation] *(s attribute) [s] "}"
+annotation-expression = "{" [s] annotation *(s attribute) [s] "}"
 ```
 
 There are several types of _expression_ that can appear in a _message_.
@@ -638,14 +639,14 @@ unrecognized _reserved-annotations_ or _private-use-annotations_ have no meaning
 
 ```abnf
 reserved-annotation = reserved-annotation-start reserved-body
-reserved-annotation-start = "!" / "@" / "%" / "*" / "+"
-                          / "<" / ">" / "?" / "~"
+reserved-annotation-start = "!" / "%" / "*" / "+" / "<" / ">" / "?" / "~"
 
 reserved-body = *([s] 1*(reserved-char / reserved-escape / quoted))
 reserved-char = %x00-08        ; omit HTAB and LF
               / %x0B-0C        ; omit CR
               / %x0E-19        ; omit SP
-              / %x21-5B        ; omit \
+              / %x21-3F        ; omit @
+              / %x41-5B        ; omit \
               / %x5D-7A        ; omit { | }
               / %x7E-D7FF      ; omit surrogates
               / %xE000-10FFFF
@@ -656,7 +657,12 @@ reserved-char = %x00-08        ; omit HTAB and LF
 **_<dfn>Markup</dfn>_** _placeholders_ are _pattern_ parts
 that can be used to represent non-language parts of a _message_,
 such as inline elements or styling that should apply to a span of parts.
-Markup comes in three forms:
+
+_Markup_ MUST begin with U+007B LEFT CURLY BRACKET `{`
+and end with U+007D RIGHT CURLY BRACKET `}`.
+_Markup_ MAY contain one more _attributes_.
+
+_Markup_ comes in three forms:
 
 **_<dfn>Markup-open</dfn>_** starts with U+0023 NUMBER SIGN `#` and
 represents an opening element within the _message_,
@@ -673,8 +679,8 @@ is a _pattern_ part ending a span.
 Unlike the other forms, it does not include _options_.
 
 ```abnf
-markup       = "{" [s] markup-open [s] ["/"] "}"
-             / "{" [s] markup-close [s] "}"
+markup       = "{" [s] markup-open *(s attribute) [s] ["/"] "}"
+             / "{" [s] markup-close *(s attribute) [s] "}"
 markup-open  = "#" identifier *(s option)
 markup-close = "/" identifier
 ```
@@ -691,6 +697,42 @@ _Markup_ _placeholders_ can appear in any order without making the _message_ inv
 However, specifications or implementations defining _markup_ might impose requirements
 on the pairing, ordering, or contents of _markup_ during _formatting_.
 
+## Attributes
+
+**_Attributes_ are reserved for standardization by future versions of this specification.**
+Examples in this section are meant to be illustrative and
+might not match future requirements or usage.
+
+An **_<dfn>attribute</dfn>_** is an _identifier_ with an optional value
+that appears in an _expression_ or in _markup_.
+
+_Attributes_ are prefixed by a U+0040 COMMERCIAL AT `@` sign,
+followed by an _identifier_.
+An _attribute_ MAY have a _value_ which is separated from the _identifier_
+by an U+003D EQUALS SIGN `=` along with optional whitespace.
+The _value_ of an _attribute_ can be either a _literal_ or a _variable_.
+
+Multiple _attributes_ are permitted in an _expression_ or _markup_.
+Each _attribute_ is separated by whitespace.
+
+```abnf
+attribute = "@" identifier [[s] "=" [s] (literal / variable)]
+```
+
+> Examples of _expressions_ and _markup_ with _attributes_:
+>
+> A _message_ including a _literal_ that should not be translated:
+>
+> ```
+> In French, "{|bonjour| @translate=no}" is a greeting
+> ```
+>
+> A _message_ with _markup_ that should not be copied:
+>
+> ```
+> Have a {+span @can-copy}great and wonderful{-span @can-copy} birthday!
+> ```
+
 ## Other Syntax Elements
 
 This section defines common elements used to construct _messages_.